Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

07/23/2018
by   Ahmet Iscen, et al.
0

State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founded hybrid filtering approach allowing full control of the space-time trade-off between these two extremes. Experimentally, we verify that our hybrid method delivers results on par with the state of the art, with lower memory demands compared to spectral filtering approaches and faster compared to temporal filtering.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/20/2017

Fast Spectral Ranking for Similarity Search

Despite the success of deep learning on representing images for particul...
research
11/27/2018

Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing

Diffusion is commonly used as a ranking or re-ranking method in retrieva...
research
09/24/2016

Three Tiers Neighborhood Graph and Multi-graph Fusion Ranking for Multi-feature Image Retrieval: A Manifold Aspect

Single feature is inefficient to describe content of an image, which is ...
research
09/24/2016

Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval

Incompatibility of image descriptor and ranking is always neglected in i...
research
12/15/2022

Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time

We pose video object segmentation as spectral graph clustering in space ...
research
07/05/2019

A Spectral Approach to Unsupervised Object Segmentation in Video

We formulate object segmentation in video as a graph partitioning proble...
research
11/14/2017

Similarity-Aware Spectral Sparsification by Edge Filtering

In recent years, spectral graph sparsification techniques that can compu...

Please sign up or login with your details

Forgot password? Click here to reset